Agent Plugins Marketplace
← All plugins

adversarial-review

v1.5.0

Hostile, bias-free review using independent reviewers, false-positive verification, and validated fixes.

CodexClaude Code2 Skills

By Patrick D'appollonioLicense: MIT8 GitHub starsUpdated last week

Directory evidence

Runtimes
Codex and Claude Code
Parsed components
2 skill or MCP entries
Source updated
Sep 17, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install adversarial-review for Codex and Claude Code

Installs for the current user
codex plugin marketplace add patrickdappollonio/claude-plugins
codex plugin marketplace upgrade patrickdappollonio
codex plugin add adversarial-review@patrickdappollonio

Paste and run these commands in a terminal with Codex. They add and refresh the patrickdappollonio catalog, then install this plugin.

Compatibility: the page URL and API slug “adversarial-review” remain stable.

  • Codex: adversarial-review@agent-plugin-marketplace → adversarial-review@patrickdappollonio

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/patrickdappollonio/claude-plugins

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/adversarial-review/.

Plugin files

plugins/adversarial-review/
├── .codex-plugin/plugin.json
├── .claude-plugin/plugin.json
├── skills/adversarial-review/SKILL.md
└── skills/adversarial-review-quick/SKILL.md

Included Skills2

adversarial-reviewskills/adversarial-review/SKILL.md

Use when you want a hostile, bias-free review of a code change — a PR, the last commit, or local/uncommitted work — that attacks it from many independent angles (conformance to the approved design, whether that design was right in the first place, concurrency, failure injection, input and auth attacks, data integrity, resource exhaustion, observability, API contract, maintainability, simplicity and scope creep, root-cause/incomplete-fix consistency, rollback, tests, AI-slop, fact-checking). Especially for AI-generated code that looks right but may be hollow, when a change should be checked against a plan or mock that was signed off, or when you want claims in comments and commit messages fact-checked rather than trusted. This is the full panel and it is token-heavy: if the user asks for a smaller, quicker, lighter, or cheaper adversarial review, use the `adversarial-review-quick` skill instead.

adversarial-review-quickskills/adversarial-review-quick/SKILL.md

Use when you want a smaller, quicker, cheaper adversarial review of a code change — "a smaller adversarial review", "a quick adversarial review", "a light adversarial review", "adversarial review but don't burn tokens" — or when you want to choose which adversarial reviewers run. Proposes the fewest reviewers that strictly fit the change, shows the full roster, and lets the user add or drop any before anything runs. It keeps the same verifier and fix validator as the full panel. Prefer this over `adversarial-review` whenever the user asks for a smaller/quick/light/cheap one or wants to pick reviewers; use the full skill when they ask for a thorough or complete review.

Plugin manifests2

plugins/adversarial-review/.codex-plugin/plugin.json
{
  "name": "adversarial-review",
  "version": "1.5.0",
  "description": "Hostile, bias-free review using independent reviewers, false-positive verification, and validated fixes.",
  "author": {
    "name": "Patrick D'appollonio",
    "email": "[email protected]"
  },
  "homepage": "https://gist.github.com/patrickdappollonio/2fc5af4d714b97802072e97422823bc4",
  "license": "MIT",
  "keywords": [
    "code-review",
    "security",
    "quality",
    "adversarial"
  ],
  "skills": "./skills/",
  "interface": {
    "displayName": "Adversarial Review",
    "shortDescription": "Challenge a change from independent angles.",
    "longDescription": "Runs full and quick adversarial review panels, verifies proposed findings, and reports only confirmed problems with validated fixes.",
    "developerName": "Patrick D'appollonio",
    "category": "Developer Tools",
    "capabilities": [
      "Review",
      "Analyze"
    ],
    "defaultPrompt": [
      "Give this change an adversarial review.",
      "Run a quick adversarial review."
    ]
  }
}
plugins/adversarial-review/.claude-plugin/plugin.json
{
  "name": "adversarial-review",
  "description": "Hostile, bias-free review of a change — dispatches independent adversarial reviewers that hold the code against what was agreed and question whether what was agreed was right, plus a standalone false-positive filter, and reports only verified findings in plain language. Ships a full 18-reviewer panel and a cheaper quick panel that proposes the fewest reviewers that fit the change, lets you add or drop any, and keeps both verification gates.",
  "version": "1.5.0",
  "author": {
    "name": "Patrick D'appollonio",
    "email": "[email protected]"
  },
  "homepage": "https://gist.github.com/patrickdappollonio/2fc5af4d714b97802072e97422823bc4",
  "license": "MIT",
  "keywords": [
    "code-review",
    "security",
    "quality",
    "adversarial",
    "pre-merge"
  ]
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[adversarial-review on Agent Plugins Marketplace](https://pluginsmp.com/plugins/adversarial-review)